arXiv subjects

Alexander Bauer

Publications and source records attributed to Alexander Bauer.

12 recordsLinked to original sources

arXiv2026

Rethinking Structural Anomaly Detection: From Decision Boundaries to Projection Operators

Most existing anomaly detection methods rely on estimating a probability density or learning an enclosing decision boundary, implicitly assuming that normal data occupies a region of non-zero volume in the ambient space. In contrast, structural anomaly detection considers data that lies near a low-dimensional manifold, creating a mismatch between the inductive bias of existing methods and the structure of the data, often resulting in degraded performance. To address this mismatch, we introduce a geometric perspective. Specifically, we learn a projection operator onto the manifold of normal samples and define a sample as anomalous if it is altered by this projection. This formulation naturally integrates the inductive bias of manifold-supported data and reframes anomaly detection in terms of a projection residual, thereby resolving issues arising from modeling degenerate distributions. Notably, it provides a unifying interpretation of reconstruction-based methods by explaining their success and failure in terms of projection quality. In particular, it explains the strong generalization ability of projection-aligned models as a consequence of contraction behavior toward the manifold. Moreover, by decoupling anomaly detection from probabilistic modeling, it reduces the tendency to misclassify rare but normal samples, a widely recognized limitation of existing approaches. Empirically, we demonstrate that projection-aligned methods achieve strong performance, outperforming boundary-based methods while improving upon existing reconstruction-based approaches.

cs.LG↗

arXiv2025

Noise & pattern: identity-anchored Tikhonov regularization for robust structural anomaly detection

Anomaly detection plays a pivotal role in automated industrial inspection, aiming to identify subtle or rare defects in otherwise uniform visual patterns. As collecting representative examples of all possible anomalies is infeasible, we tackle structural anomaly detection using a self-supervised autoencoder that learns to repair corrupted inputs. To this end, we introduce a corruption model that injects artificial disruptions into training images to mimic structural defects. While reminiscent of denoising autoencoders, our approach differs in two key aspects. First, instead of unstructured i.i.d.\ noise, we apply structured, spatially coherent perturbations that make the task a hybrid of segmentation and inpainting. Second, and counterintuitively, we add and preserve Gaussian noise on top of the occlusions, which acts as a Tikhonov regularizer anchoring the Jacobian of the reconstruction function toward identity. This identity-anchored regularization stabilizes reconstruction and further improves both detection and segmentation accuracy. On the MVTec AD benchmark, our method achieves state-of-the-art results (I/P-AUROC: 99.9/99.4), supporting our theoretical framework and demonstrating its practical relevance for automatic inspection.

cs.CV↗

arXiv2025

ConStellaration: A dataset of QI-like stellarator plasma boundaries and optimization benchmarks

Stellarators are magnetic confinement devices under active development to deliver steady-state carbon-free fusion energy. Their design involves a high-dimensional, constrained optimization problem that requires expensive physics simulations and significant domain expertise. Recent advances in plasma physics and open-source tools have made stellarator optimization more accessible. However, broader community progress is currently bottlenecked by the lack of standardized optimization problems with strong baselines and datasets that enable data-driven approaches, particularly for quasi-isodynamic (QI) stellarator configurations, considered as a promising path to commercial fusion due to their inherent resilience to current driven disruptions. Here, we release an open dataset of diverse QI-like stellarator plasma boundary shapes, paired with their ideal magnetohydrodynamic (MHD) equilibria and performance metrics. We generated this dataset by sampling a variety of QI fields and optimizing corresponding stellarator plasma boundaries. We introduce three optimization benchmarks of increasing complexity: (1) a single objective geometric optimization problem, (2) a "simple-to-build" QI stellarator, and (3) a multi-objective ideal-MHD stable QI stellarator that investigates trade-offs between compactness and coil simplicity. For every benchmark, we provide reference code, evaluation scripts, and strong baselines based on classical optimization techniques. Finally, we show how learned models trained on our dataset can efficiently generate novel, feasible configurations without querying expensive physics oracles. By openly releasing the dataset along with benchmark problems and baselines, we aim to lower the entry barrier for optimization and machine learning researchers to engage in stellarator design and to accelerate cross-disciplinary progress toward bringing fusion energy to the grid.

cs.LG↗

arXiv2022

Self-Supervised Training with Autoencoders for Visual Anomaly Detection

We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. Here, regularized autoencoders provide a popular approach by learning the identity mapping on the set of normal examples, while trying to prevent good reconstruction on points outside of the manifold. Typically, this goal is implemented by controlling the capacity of the model, either directly by reducing the size of the bottleneck layer or implicitly by imposing some sparsity (or contraction) constraints on parts of the corresponding network. However, neither of these techniques does explicitly penalize the reconstruction of anomalous signals often resulting in poor detection. We tackle this problem by adapting a self-supervised learning regime that exploits discriminative information during training but focuses on the submanifold of normal examples. Informally, our training objective regularizes the model to produce locally consistent reconstructions, while replacing irregularities by acting as a filter that removes anomalous patterns. To support this intuition, we perform a rigorous formal analysis of the proposed method and provide a number of interesting insights. In particular, we show that the resulting model resembles a non-linear orthogonal projection of partially corrupted images onto the submanifold of uncorrupted samples. On the other hand, we identify the orthogonal projection as an optimal solution for a number of regularized autoencoders including the contractive and denoising variants. We support our theoretical analysis by empirical evaluation of the resulting detection and localization performance of the proposed method. In particular, we achieve a new state-of-the-art result on the MVTec AD dataset -- a challenging benchmark for visual anomaly detection in the manufacturing domain.

cs.CV↗

arXiv2021

Registration for Incomplete Non-Gaussian Functional Data

Accounting for phase variability is a critical challenge in functional data analysis. To separate it from amplitude variation, functional data are registered, i.e., their observed domains are deformed elastically so that the resulting functions are aligned with template functions. At present, most available registration approaches are limited to datasets of complete and densely measured curves with Gaussian noise. However, many real-world functional data sets are not Gaussian and contain incomplete curves, in which the underlying process is not recorded over its entire domain. In this work, we extend and refine a framework for joint likelihood-based registration and latent Gaussian process-based generalized functional principal component analysis that is able to handle incomplete curves. Our approach is accompanied by sophisticated open-source software, allowing for its application in diverse non-Gaussian data settings and a public code repository to reproduce all results. We register data from a seismological application comprising spatially indexed, incomplete ground velocity time series with a highly volatile Gamma structure. We describe, implement and evaluate the approach for such incomplete non-Gaussian functional data and compare it to existing routines.

stat.ME↗

arXiv2021

Mundus vult decipi, ergo decipiatur: Visual Communication of Uncertainty in Election Polls

Election poll reporting often focuses on mean values and only subordinately discusses the underlying uncertainty. Subsequent interpretations are too often phrased as certain. Moreover, media coverage rarely adequately takes into account the differences between now- and forecasts. These challenges were ubiquitous in the context of the 2016 and 2020 U.S. presidential elections, but are also present in multi-party systems like Germany. We discuss potential sources of bias in nowcasting and forecasting and review the current standards in the visual presentation of survey-based nowcasts. Concepts are presented to attenuate the issue of falsely perceived accuracy. We discuss multiple visual presentation techniques for central aspects in poll reporting. One key idea is the use of Probabilities of Events instead of party shares. The presented ideas offer modern and improved ways to communicate (changes in) the electoral mood for the general media.

cs.CY↗

arXiv2019

Polynomial-Time Exact MAP Inference on Discrete Models with Global Dependencies

Considering the worst-case scenario, junction tree algorithm remains the most general solution for exact MAP inference with polynomial run-time guarantees. Unfortunately, its main tractability assumption requires the treewidth of a corresponding MRF to be bounded strongly limiting the range of admissible applications. In fact, many practical problems in the area of structured prediction require modelling of global dependencies by either directly introducing global factors or enforcing global constraints on the prediction variables. That, however, always results in a fully-connected graph making exact inference by means of this algorithm intractable. Previous work [1]-[4] focusing on the problem of loss-augmented inference has demonstrated how efficient inference can be performed on models with specific global factors representing non-decomposable loss functions within the training regime of SSVMs. In this paper, we extend the framework for an efficient exact inference proposed in in [3] by allowing much finer interactions between the energy of the core model and the sufficient statistics of the global terms with no additional computation costs. We demonstrate the usefulness of our method in several use cases, including one that cannot be handled by any of the previous approaches. Finally, we propose a new graph transformation technique via node cloning which ensures a polynomial run-time for solving our target problem independently of the form of a corresponding clique tree. This is important for the efficiency of the main algorithm and greatly improves upon the theoretical guarantees of the previous works.

cs.DM↗

arXiv2019

Towards Best Practice in Explaining Neural Network Decisions with LRP

Within the last decade, neural network based predictors have demonstrated impressive - and at times super-human - capabilities. This performance is often paid for with an intransparent prediction process and thus has sparked numerous contributions in the novel field of explainable artificial intelligence (XAI). In this paper, we focus on a popular and widely used method of XAI, the Layer-wise Relevance Propagation (LRP). Since its initial proposition LRP has evolved as a method, and a best practice for applying the method has tacitly emerged, based however on humanly observed evidence alone. In this paper we investigate - and for the first time quantify - the effect of this current best practice on feedforward neural networks in a visual object detection setting. The results verify that the layer-dependent approach to LRP applied in recent literature better represents the model's reasoning, and at the same time increases the object localization and class discriminativity of LRP.

cs.LG↗

arXiv2018

KOALA: A new paradigm for election coverage

Common election poll reporting is often misleading as sample uncertainty is addressed insufficiently or not covered at all. Furthermore, main interest usually lies beyond the simple party shares. For a more comprehensive opinion poll and election coverage, we propose shifting the focus towards the reporting of survey-based probabilities for specific events of interest. We present such an approach for multi-party electoral systems, focusing on probabilities of coalition majorities. A Monte Carlo approach based on a Bayesian Multinomial-Dirichlet model is used for estimation. Probabilities are estimated, assuming the election was held today (''now-cast''), not accounting for potential shifts in the electorate until election day ''fore-cast''. Since our method is based on the posterior distribution of party shares, the approach can be used to answer a variety of questions related to the outcome of an election. We also introduce visualization techniques that facilitate a more adequate depiction of relevant quantities as well as respective uncertainties. The benefits of our approach are discussed by application to the German federal elections in 2013 and 2017. An open source implementation of our methods is freely available in the R package coalitions.

stat.AP↗

arXiv2017

Optimizing for Measure of Performance in Max-Margin Parsing

Many statistical learning problems in the area of natural language processing including sequence tagging, sequence segmentation and syntactic parsing has been successfully approached by means of structured prediction methods. An appealing property of the corresponding discriminative learning algorithms is their ability to integrate the loss function of interest directly into the optimization process, which potentially can increase the resulting performance accuracy. Here, we demonstrate on the example of constituency parsing how to optimize for F1-score in the max-margin framework of structural SVM. In particular, the optimization is with respect to the original (not binarized) trees.

cs.CL↗

arXiv2017

Partial Optimality of Dual Decomposition for MAP Inference in Pairwise MRFs

Markov random fields (MRFs) are a powerful tool for modelling statistical dependencies for a set of random variables using a graphical representation. An important computational problem related to MRFs, called maximum a posteriori (MAP) inference, is finding a joint variable assignment with the maximal probability. It is well known that the two popular optimisation techniques for this task, linear programming (LP) relaxation and dual decomposition (DD), have a strong connection both providing an optimal solution to the MAP problem when a corresponding LP relaxation is tight. However, less is known about their relationship in the opposite and more realistic case. In this paper, we explain how the fully integral assignments obtained via DD partially agree with the optimal fractional assignments via LP relaxation when the latter is not tight. In particular, for binary pairwise MRFs the corresponding result suggests that both methods share the partial optimality property of their solutions.

cs.DS↗

arXiv2012

Pair-copula Bayesian networks

Pair-copula Bayesian networks (PCBNs) are a novel class of multivariate statistical models, which combine the distributional flexibility of pair-copula constructions (PCCs) with the parsimony of conditional independence models associated with directed acyclic graphs (DAG). We are first to provide generic algorithms for random sampling and likelihood inference in arbitrary PCBNs as well as for selecting orderings of the parents of the vertices in the underlying graphs. Model selection of the DAG is facilitated using a version of the well-known PC algorithm which is based on a novel test for conditional independence of random variables tailored to the PCC framework. A simulation study shows the PC algorithm's high aptitude for structure estimation in non-Gaussian PCBNs. The proposed methods are finally applied to modelling financial return data.

stat.ME↗